Blackmores’ Chatbot Helps People Live Better
In an effort to use digital marketing to activate their brand presence at the Australian Open, Blackmores teamed up with creative technologists at S1T2 and Bastion EBA to develop the Well Bot, an interactive chatbot able to intuitively kickstart the conversation about healthier living. Designed to converse with users over Facebook Messenger or SMS, the Well Bot used interactions and artificial intelligence to assess each user’s greatest health and wellbeing weakness and sign them up to a specially developed Action Plan.
The resulting chatbot and moderation application used web development and artificial intelligence to develop a more innovative approach to connecting with customers. Using a combination of natural language processing and pre-defined responses, the Well Bot engages users in meaningful conversations about healthy living through the existing technological framework of their everyday lives. By translating Blackmore’s pledge to help people live better into an interactive digital marketing application, the Well Bot creates a collaborative brand experience that adds value both to the brand and to its customers.
Interconnected Web Services and Natural Language Processing
Implementation of natural language processing was crucial to the aim of facilitating meaningful conversations between the digital marketing platform and users. By allowing users to interact directly with the chatbot in their own words, the technology enhanced the feeling of connection and customisation. However, in order to mitigate the limitations of this relatively new technology, we also applied a system of pre-defined responses as a way of giving structure to each interaction. This allowed the chatbot to steer users towards more productive discussions and the end goal of registering them for a Blackmores Action Plan.
To ensure that the chatbot was able to adapt to suit real-life use cases, S1T2 combined an iterative development schedule with systems of adaptive machine learning. With the unpredictability of real-life interactions in mind, we developed the Well Bot in a way that enabled it to recognise and communicate holes in its own logic. Implementing an iterative web development process then allowed S1T2 to fill gaps in the system as they appeared. In this way, we were able to ensure that the chatbot adapted and improved according to real-life user interaction.
- Dynamo NoSQL,
- Python 2.7.
- Facebook Messenger Graph API,
- Marketo REST API,
- Twilio REST API.
External Integration and Security
Harnessing the increased levels of consumer interest in chatbot technology, the Well Bot was designed to facilitate realistic and meaningful conversations. In order to implement the wide-ranging integration that was so important to the Well Bot’s usability, we created a unique set of APIs during the web development process to allow the chatbot to integrate with external interfaces (e.g. bot activation). The system was housed in the cloud using a AWS multi-tier system architecture which gave strict control over all interface connections. This tiered structure enabled us to protect user data while ensuring greater stability across each of the digital marketing campaign’s different communication interfaces.
To that end, great focus was placed on understanding the ideal user experience of the application. This fostered comfortable and secure conversations between the user and the chatbot, creating an engaging experience for audiences that simultaneously increased brand awareness for Blackmores.